OpenAI’s new Ultrafast tier runs GPT-5.6 Sol on Cerebras chips
All about: OpenAI models and products →
Ultrafast, a new service tier in the OpenAI API, pushes GPT-5.6 Sol to up to 750 output tokens per second. OpenAI says that’s up to 14x the model’s normal speed.
The tier is in preview and starts with a limited group of API customers. OpenAI plans to widen access as capacity grows.
Up next
Opus 5 tops a new conceptual reasoning index at 73.6
Redwood Research and Anthropic released CRI, an index for reasoning tasks that have no verifiable answer. As of August 10, 2026, Opus 5 leads with 73.6 points (±2.1), against a ceiling the authors put at roughly 91. Scores have climbed almost linearly since late 2024.
Related stories
- Zhipu AI will release GLM-5.3 weights in stages after safety reviews
- OpenAI’s Habitat grew from a Python library to 22M req/sec
- Bloomberg: OpenAI backs bills to cut China’s AI chip access
- Google’s TPU Sync cut TTFT by up to 90% in its own tests
- OpenAI’s CFO keeps data center spending after midterms
- OpenAI’s Pando cut monorepo push latency nearly 5x
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

